Pointwise ABC, MonoT5, New Unit Tests #128
Merged
+729
−104
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…filename into the init function in PointwiseRankLLM, add PromptMode.MONOT5 = monot5 as prompt_mode
Pointwise changes
|
Changes:
|
ronakice
reviewed
Aug 6, 2024
Merged
XKTZ
added a commit
to XKTZ/rank_llm
that referenced
this pull request
Aug 7, 2024
…rting docs to prompts in pointwise by using the listwise functions, fix sorting order of monot5, add batching for run_llm_batched in pointwise_rankllm
…g to pointwise_rankllm class instead of individual pointwise model classes
ronakice
approved these changes
Aug 17, 2024
Comment on lines
16
to
22
| try: | ||
| from vllm import LLM, SamplingParams | ||
| except: | ||
| LLM = None | ||
| SamplingParams = None | ||
|
|
||
| logger = logging.getLogger(__name__) |
| self, | ||
| model: str, | ||
| prompt_mode: str = "monot5", | ||
| context_size: int = 512, |
There was a problem hiding this comment.
Create a new issue s.t., we support longer sequences eventually, nothing is limiting T5 usage with longer context (we've done it before)
Comment on lines
+73
to
+75
| truth_logit = logit_tensor[1176] | ||
| false_logit = logit_tensor[6136] | ||
| score = math.exp(truth_logit) / ( |
There was a problem hiding this comment.
this is hardcoded and won't scale in the future to other T5 base models, note this as a T5 todo
| outputs = self._tokenizer.decode( | ||
| output_ids, skip_special_tokens=True, spaces_between_special_tokens=False | ||
| ) | ||
| truth_logit = logits[0][0][1176] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary of Changes
extract_kwargsfunctionretrieve_and_rerankRank_LLMABC parameters (missing kwargs)...more changes below (@IR3KT4FUNZ)